{"id":"W4323047767","doi":"10.7554/elife.84874.1","title":"Expanding the stdpopsim species catalog, and lessons learned for realistic genome simulations","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Evolution and Genetic Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Biotechnology and Biological Sciences Research Council; Science for Life Laboratory; Knut och Alice Wallenbergs Stiftelse; Brown University; Deutsche Forschungsgemeinschaft; University of Edinburgh; Robertson Foundation; National Institutes of Health; National Science Foundation","keywords":"Inference; Population; Computer science; Sophistication; Genome; Crossover; Obstacle; Benchmarking; Data science; Computational biology; Biology; Data mining; Machine learning; Geography; Artificial intelligence; Genetics; Gene","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009655208,0.001457321,0.001315256,0.002194836,0.001186829,0.003583364,0.007719506,0.001923327,0.01551194],"category_scores_gemma":[0.03151456,0.001546699,0.002167562,0.002840251,0.0009842991,0.007236586,0.005170674,0.00509991,0.007029624],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001605398,"about_ca_system_score_gemma":0.004147754,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0110675,"about_ca_topic_score_gemma":0.01009978,"domain_scores_codex":[0.9975617,0.0008171446,0.0002386633,0.0003438475,0.0008636506,0.0001749119],"domain_scores_gemma":[0.9861003,0.005242285,0.0004593613,0.003680895,0.00325916,0.001257979],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001032794,0.0003914565,0.02163439,0.002290703,0.0004124512,0.0007467642,0.0009145342,0.3311224,0.008606462,0.1434079,0.2683677,0.2210723],"study_design_scores_gemma":[0.0003258141,0.000114566,0.002087109,0.0006390632,0.00009496979,0.0002452554,0.0001454412,0.5398774,0.005743383,0.07151323,0.379014,0.0001997665],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0567573,0.004244293,0.7221749,0.01054069,0.002633862,0.0005548521,0.04202374,0.1227901,0.03828013],"genre_scores_gemma":[0.1181304,0.003352048,0.7752208,0.00218341,0.000405086,0.001109093,0.06579334,0.0299259,0.00387994],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01551194,"threshold_uncertainty_score":0.05189258,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08952258160607916,"score_gpt":0.3586664035120297,"score_spread":0.2691438219059505,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}